Data-driven engineering material ultra-high cycle fatigue life prediction method

Abstract

The invention discloses a data-driven engineering material ultra-high cycle fatigue life prediction method. The method comprises the following steps: firstly, collecting engineering material information and ultra-high cycle fatigue data to form initial sample data, and dividing the data into a test set and a training set; secondly, evaluating the contribution degree of each input characteristic variable to an output variable according to an existing physical model, sorting the importance of the characteristic variables, then, screening out key characteristic variables, and forming a target function of a data-driven model; embedding the target function into a machine learning algorithm to obtain an intermediate calculated value Z, and evaluating the prediction precision of the data-driven model by adopting a decision coefficient R2; and finally, associating the training set Z value with the fatigue life to realize the ultra-high cycle fatigue life prediction of the engineering material. According to the method, main influence factors of the ultra-high cycle fatigue life of the engineering material are combined with the data driving algorithm, the ultra-high cycle fatigue life of the engineering material can be quickly and effectively predicted, and a good implementation effect is achieved in defect-containing materials such as weld joints.

Description

technical field [0001] The invention belongs to the technical field of material life evaluation and relates to a data-driven ultra-high-cycle fatigue life prediction method for engineering materials. Background technique [0002] In recent years, many engineering equipments have shown a new trend of long-life service, and the cyclic loads of some components will exceed 10 10 cycles, therefore, trying to quantitatively describe the ultra-high cycle fatigue behavior of engineering materials and establish related prediction models is an inevitable requirement for the ultra-long life design of engineering structures. Most of the traditional fatigue life prediction models are obtained by fitting test data. The test cost is high, the cycle is long, and there are also great limitations (for example, the model is only applicable under a certain working condition). In order to serve engineering needs, it is urgent It is necessary to seek an efficient method for predicting the ultra-...

AI Technical Summary

Problems solved by technology

[0004] At present, there are few theoretical models for the prediction of ultra-high cycle fatigue life of engineering materials. Zhu Mingliang et al. proposed an ultra-high cycle fatigue life prediction model based on stress level, defect size and defect location factors (Z parameter Model) [Zhu Mingliang et al. A new model for ultra-high cycle fatigue life prediction, China Science and Technology Papers Online Excellent Paper, 2012.], although this model is applicable within a certain range, it still has its limitations

Images